80 Commits

Author SHA1 Message Date
liuzc
61bc5bd0dd support resize embed for zero3
Former-commit-id: a5f6a7f4fb057511428011c37422c535f31b79d2
2024-01-16 15:16:20 +08:00
hiyouga
61960189b2 fix #1789
Former-commit-id: 4571068e1e00dc234c9131185fe0924c726add84
2024-01-09 18:31:27 +08:00
hiyouga
f53bc7d9a0 fix #2127
Former-commit-id: ebee4f6a2a20a39ad7fbb87edfa63e244da7b5e6
2024-01-09 14:49:13 +08:00
hiyouga
6bbcf5ad16 improve model export
Former-commit-id: d2a676c8ba550e1dd7f4e12cb397a32e01831d85
2024-01-05 18:51:49 +08:00
hiyouga
7c50959fe6 fix #2098
Former-commit-id: f6fdd83f8a6bf3e48cf08fd098ec7b08d34d16d7
2024-01-05 17:11:26 +08:00
hiyouga
dc8714a003 fix #2081
Former-commit-id: 33f2c0d4f89cf76671c0fdfbcee79d732b6a020e
2024-01-04 23:19:08 +08:00
hiyouga
3fff67e3c7 fix dispatch
Former-commit-id: 1696698eb980fef36a44f860105711bc06d674c9
2024-01-03 16:33:16 +08:00
hiyouga
eb021ca748 fix valuehead patch
Former-commit-id: 24d8d6f224ccb98387ec72e688fa32f5f308dd07
2024-01-03 16:19:23 +08:00
hiyouga
1a86cc3078 fix rm server
Former-commit-id: 55021097d565536a68113ee33af31beaff38334e
2024-01-03 15:30:46 +08:00
hiyouga
afa3c86391 fix version
Former-commit-id: 47da742fc971520a697ed5ce611f8d6de61ab22b
2023-12-29 04:53:36 +08:00
hiyouga
498b83d77a fix bug
Former-commit-id: e4bb846c43c087bfdd99d0c9eb0318e95b943977
2023-12-24 19:20:12 +08:00
hiyouga
2a3980d6ba update loader
Former-commit-id: 6629087e12f64f2635f24311234202077814083c
2023-12-24 19:10:23 +08:00
hiyouga
5d440f978e update patcher
Former-commit-id: e44b82ee245a7ee99057c7b58b1edef5c222dc1f
2023-12-23 15:24:27 +08:00
hiyouga
a7fc20cb2d fix unsloth dtype
Former-commit-id: 779cfefb7841d00fc712a5f5addf0fe3eb14c6fd
2023-12-23 01:59:49 +08:00
hiyouga
938c4cb132 fix dpo trainer
Former-commit-id: 074745b1707f98e092749f57041d866c5d55bc04
2023-12-23 01:51:55 +08:00
hiyouga
f0d405f392 support unsloth
Former-commit-id: 7aad0b889d9a316fffd65f32a419078418fc0986
2023-12-23 00:14:33 +08:00
ShaneTian
3eaabe12aa Fix slow model initialization in bfloat16 dtype.
Former-commit-id: d032daa4bd598dd0d71b43eb68a614de77a699a6
2023-12-22 16:27:28 +08:00
hiyouga
fee0fef052 fix ds zero3 check
Former-commit-id: 083355fc051f5d25400eb80887ff5e0d15ce729b
2023-12-21 01:19:22 +08:00
hiyouga
de6be321b9 match version
Former-commit-id: af0194e6d9ba1c67a8592c840c01cee7991b0b0e
2023-12-20 22:17:35 +08:00
hiyouga
23a875a8b1 improve quantization
Former-commit-id: 624cc212819b7cd16295c72084cd454b67cf89a6
2023-12-20 18:27:16 +08:00
hiyouga
c1233ab65f add max_memory for gptq #1923
Former-commit-id: c4a3977ad7278b59a9b3dadcb446bb4c99da5c9d
2023-12-20 18:15:17 +08:00
hiyouga
a862ce636f fix mixtral inference #1821
Former-commit-id: f86857bd9ef456e77ad79a584f1fa08a129e5270
2023-12-20 15:11:15 +08:00
hiyouga
e06b9c4fa1 fix #1900
Former-commit-id: 0c6ab7c75e671348f24d28309d450aecec0a157f
2023-12-19 17:21:46 +08:00
hiyouga
8154b4bdf6 fix #1742
Former-commit-id: 870426ff70c060213ac283b10a9b1f4bf71679ef
2023-12-16 20:50:45 +08:00
hiyouga
7c362509a6 add noisy mean initialization #1815
Former-commit-id: a66186b8724ffd0351a32593ab52d8a2312f339b
2023-12-16 19:47:51 +08:00
hiyouga
4e75ca1222 support dpo-ftx
Former-commit-id: b87c74289d523ef88611b376074199ffd03cf103
2023-12-16 19:21:41 +08:00
hiyouga
f0f9d253d8 support autogptq in llama board #246
Former-commit-id: 71389be37cb0f1a65db6e501e11ca14e615c1a24
2023-12-16 16:31:30 +08:00
hiyouga
7dbc670902 support quantization in export model
Former-commit-id: 3524aa1e58da94ab00e9a2024952ea1b4119b2af
2023-12-15 23:44:50 +08:00
hiyouga
2db4cfab40 update dc link
Former-commit-id: 87ef3f47b519677e6a7c81ff45584acb34339f3a
2023-12-15 22:11:31 +08:00
hiyouga
329576a5b4 fix bug
Former-commit-id: 00c77104f8f9675e1421f99d78de710b21cab047
2023-12-15 21:54:02 +08:00
hiyouga
f32c8614c2 fix bug
Former-commit-id: 9e509b99af95666ea27f5540bedd64a330357ad7
2023-12-15 21:49:26 +08:00
hiyouga
d24d2f0458 add configurer
Former-commit-id: 2740aa9cbbcfc6dcfef82915b7db4e0f8b2c1bae
2023-12-15 21:46:40 +08:00
hiyouga
bd03307bbd refactor adapter hparam
Former-commit-id: 0716f5e470afffd2df5a815712b552a4b4797153
2023-12-15 20:53:11 +08:00
hiyouga
6a186d4386 add loftq
Former-commit-id: d4c351f1ec82b0864cc32c5602b03daddf9aeaba
2023-12-14 21:53:56 +08:00
hiyouga
e55e32efc4 fix valuehead model
Former-commit-id: bfdee1608f53a6334d8e73c48dbeb4160969d783
2023-12-14 20:15:20 +08:00
hoshi-hiyouga
fa99ead86b tiny fix
Former-commit-id: 81167cd19dac4926da9bd259f4e3cb064c22825c
2023-12-13 17:32:36 +08:00
hoshi-hiyouga
3f8d33695c revert peft version
Former-commit-id: 9b0630f84fe8eaae7a5a3123626807408645521f
2023-12-13 10:49:45 +08:00
hoshi-hiyouga
ad1860d35e update peft version
Former-commit-id: 573a12c86b6ccd9085d4cbeebcbdbfcc24e1990e
2023-12-13 10:23:51 +08:00
hoshi-hiyouga
657dff438c tiny fix
Former-commit-id: 6953096c9d8f85d56cc980a4bec3a052411fb4a0
2023-12-13 10:21:29 +08:00
hoshi-hiyouga
5b211cfbe9 fix #1819
Former-commit-id: 1fcd545c3dd78bd2113cde8ef788c5395de11c34
2023-12-13 10:14:01 +08:00
hiyouga
15b321da8e remove loftq
Former-commit-id: 3a8a50d4d42082b3bdce549653b398e49f2eb554
2023-12-13 01:53:46 +08:00
hiyouga
4c69025a83 support loftq
Former-commit-id: 6219dfbd9377528bce286c724ae2dd0090881095
2023-12-12 22:47:06 +08:00
hiyouga
1a0bdd305c support system column #1765
Former-commit-id: 0a9c6e0146ebc71d5438c837463d6ab236e227c4
2023-12-12 19:45:59 +08:00
hiyouga
cefc0b2f03 fix modelscope data hub
Former-commit-id: d5b2c57a356539df9993e4774b856231eca8a6da
2023-12-12 18:33:06 +08:00
hiyouga
bd28dd0fe6 update readme
Former-commit-id: 8cace7780867dd78760f40c46fd5b6ddd47dea0a
2023-12-12 11:44:30 +08:00
hiyouga
b7d99ad5f4 support mixtral
Former-commit-id: 96380f5e1887bb166be339e58ab8f65e464d4010
2023-12-12 11:39:04 +08:00
hiyouga
e3e86340ec fix baichuan resize
Former-commit-id: f4657de7d574fdab5d164c679bd474d35140894a
2023-12-11 20:55:50 +08:00
hiyouga
2e42e38ff2 tiny fix
Former-commit-id: 0239d29fa02a88b50f27caa706834f3c3ce0262d
2023-12-11 18:09:40 +08:00
hiyouga
9ead5a2d21 support resize embeddings #1786
Former-commit-id: 64744dde89ccb9a24a46985a99151ad2dde03919
2023-12-11 17:50:02 +08:00
hiyouga
5819eb7121 use peft 0.7.0, fix #1561 #1764
Former-commit-id: 9ce1b0e2f21a4601defe8e8f1f3f312626abe3d8
2023-12-11 17:13:40 +08:00